add test module

sentence_api/models.py

@@ -1,4 +1,5 @@
-from typing import List, Optional
+from datetime import datetime
+from typing import Dict, List, Literal, Optional
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
@@ -10,6 +11,8 @@ class SentenceBoundary(BaseModel):
     start_ms: int = Field(ge=0)
     end_ms: int = Field(gt=0)
     text: Optional[str] = None
+    language: Optional[str] = None
+    reference_speech_duration_ms: Optional[int] = Field(default=None, gt=0)
 
     @model_validator(mode="after")
     def validate_range(self):
@@ -46,3 +49,79 @@ class SentenceBoundaryDocument(BaseModel):
                 raise ValueError("sentence end_ms cannot exceed duration_ms")
             previous_end = sentence.end_ms
         return self
+
+
+VideoStatus = Literal["uploaded", "processing", "ready", "failed"]
+
+
+class VideoSummary(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    video_hash: str
+    title: str
+    filename: str
+    content_type: str
+    size_bytes: int = Field(ge=0)
+    duration_ms: Optional[int] = Field(default=None, gt=0)
+    language: Optional[str] = None
+    status: VideoStatus
+    error_message: Optional[str] = None
+    sentence_count: int = Field(ge=0)
+    stream_url: str
+    created_at: datetime
+    updated_at: datetime
+
+
+class VideoListResponse(BaseModel):
+    videos: List[VideoSummary]
+
+
+class VideoUploadResponse(BaseModel):
+    video_hash: str
+    status: VideoStatus
+    detail_url: str
+
+
+class VideoDetailResponse(BaseModel):
+    video: VideoSummary
+    boundaries: Optional[SentenceBoundaryDocument] = None
+
+
+class SentenceTextUpdate(BaseModel):
+    text: str = Field(min_length=1, max_length=4000)
+    language: Optional[str] = Field(default=None, max_length=32)
+
+
+class TextSubstitution(BaseModel):
+    expected: str
+    actual: str
+
+
+class AssessmentResult(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    attempt_id: str
+    scoring_version: str
+    overall_score: float = Field(ge=0, le=100)
+    passed: bool
+    pass_score: float = Field(ge=0, le=100)
+    content_score: float = Field(ge=0, le=100)
+    completeness_score: float = Field(ge=0, le=100)
+    fluency_score: float = Field(ge=0, le=100)
+    pronunciation_score: Optional[float] = Field(default=None, ge=0, le=100)
+    prosody_score: Optional[float] = Field(default=None, ge=0, le=100)
+    duration_score: float = Field(ge=0, le=100)
+    pause_score: float = Field(ge=0, le=100)
+    speech_rate_score: float = Field(ge=0, le=100)
+    reference_text: str
+    recognized_text: str
+    reference_duration_ms: int = Field(gt=0)
+    reference_speech_duration_ms: int = Field(gt=0)
+    student_recording_duration_ms: int = Field(gt=0)
+    student_speech_duration_ms: int = Field(gt=0)
+    duration_ratio: float = Field(gt=0)
+    missing_tokens: List[str]
+    extra_tokens: List[str]
+    substitutions: List[TextSubstitution]
+    feedback: str
+    details: Dict[str, str] = Field(default_factory=dict)